Skip to main content

Face Profile Biometric Enhanced by Eyewitness Testimonies

Author name : MALAK ZAYED SULAIMAN ALAMRI
Publication Date : 2022-08-21
Journal Name : 2022 26th International Conference on Pattern Recognition (ICPR)

Abstract

Continuous development in surveillance systems is increasingly motivating research in biometrics to articulate unconstrained recognition of human faces. Comparative soft biometric has recently been employed to characterize eyewitness testimonies for use in a biometric system to improve the recognition accuracies of the traditional biometric systems. In this paper, we present a face profile recognition system by fusing features extracted in a traditional face recognition system and eyewitness testimonies processed in a soft biometric system to improve recognition accuracies. Here we have also demonstrated an association between our traditional face profile biometric system and the soft biometric system by numerically mapping the features extracted from a face profile to its soft biometric attributes. Our experiments on 230 subjects in XM2VTSDB dataset demonstrate 84% accuracy for traditional biometrics. The recognition rate is further improved to 98% accuracy when soft and traditional biometrics are fused.

Keywords

Face Profile، Biometric، Eyewitness Testimonies

Publication Link

https://ieeexplore.ieee.org/document/9956434

Block_researches_list_suggestions

Suggestions to read

HIDS-IoMT: A Deep Learning-Based Intelligent Intrusion Detection System for the Internet of Medical Things
Ahlem . Harchy Ep Berguiga
Generalized first approximation Matsumoto metric
AMR SOLIMAN MAHMOUD HASSAN
Structure–Performance Relationship of Novel Azo-Salicylaldehyde Disperse Dyes: Dyeing Optimization and Theoretical Insights
EBTSAM KHALEFAH H ALENEZY
“Synthesis and Characterization of SnO₂/α-Fe₂O₃, In₂O₃/α-Fe₂O₃, and ZnO/α-Fe₂O₃ Thin Films: Photocatalytic and Antibacterial Applications”
Asma Arfaoui
Contact